Sharpen a task before starting: the expert approach, what the user is really after, and the right level of specification. Use for /sharpen, /pstack:sharpen in Claude Code, or $pstack:sharpen in Codex.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
Before starting, ask how a top expert would approach this task (their raw sources, their real methods, an outside check that the result is right), what the user is really after, and whether the task is over- or underspecified. Loosen constraints that don't serve the goal as readily as you add ones that do, and leave choices that are the user's to make open instead of deciding them. Fold in only what makes the work better, not bigger, but always keep one outside check that the result is right, without narrating the framing, then do the work. Don't hand back a rewritten prompt.
Invoke manually in either host. Do not load it implicitly. Preserve explicit user constraints, authorization gates, saved model assignments and spending policy. Loosening a constraint that the user chose requires their agreement; do not treat it as an implementation convenience.
The line at the top of this page pins the label git:20261014.7ecb5c1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (1134 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
arjitj2/open-pstack · 14 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hmasotnvu2ooa4rf
GET https://markdownregistry.com/api/v1/resolve?ref=arjitj2/open-pstack/sharpen
GET https://markdownregistry.com/api/v1/blob/5ee45ddccebb72dbca14b1252e60181a7ebe38618473b8caf92592ae5dfcc4ee
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
arjitj2/open-pstack · .agents/skills/verify-open-pstack/SKILL.md · Verify Open Pstack through installed Codex and Claude Code skills and its shipped Bun CLIs. Use for real behavior…
arjitj2/open-pstack · plugins/pstack/skills/architect/SKILL.md · Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use…
arjitj2/open-pstack · plugins/pstack/skills/arena/SKILL.md · Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for…
arjitj2/open-pstack · plugins/pstack/skills/automate-me/SKILL.md · Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a…
arjitj2/open-pstack · plugins/pstack/skills/babysit/SKILL.md · Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state…
arjitj2/open-pstack · plugins/pstack/skills/benchmark-checklist/SKILL.md · Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened)…
arjitj2/open-pstack · plugins/pstack/skills/blast-radius/SKILL.md · Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe…
arjitj2/open-pstack · plugins/pstack/skills/correct/SKILL.md · Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types…
arjitj2/open-pstack · plugins/pstack/skills/create-verification-skill/SKILL.md · Generate a project-local verification skill that drives your app the way a user does — any language, framework, or…
michael-denyer/pstack-claude · plugins/pstack/skills/sharpen/SKILL.md · Sharpen a task before starting: the expert approach, what the user is really after, and the right level of…
backnotprop/pstack · skills/sharpen/SKILL.md · Sharpen a task before starting: the expert approach, what the user is really after, and the right level of…
joetawil7/first-pass · skills/sharpen/SKILL.md · Rewrites the prompt typed after the command before any work starts, then works from the rewrite. Splits a mixed-up…
creedants/pstack-t3 · skills/sharpen/SKILL.md · Sharpen a task before starting: the expert approach, what the user is really after, and the right level of…
lucasheriques/pstack · skills/sharpen/SKILL.md · Sharpen a task before starting: the expert approach, what the user is really after, and the right level of…
